4 papers
Post-Training, Finetuning, and Steering:A Field Guide for Curating Training Data
Maria Attarian, Yifan Ruan, Claas Voelcker +5
While Vision-Language-Action models have enabled impressive cross-task transfer in zero-shot settings, \emph{adaptation} methods are often necessary to achieve consistent performan…
QPILOTS: Efficient Test-Time Q-Steering for Flow Policies
Yifan Ruan, Chenyang Cao, Andreas Burger +7
Flow-matching and diffusion policies are expressive action generators, but optimizing them with temporal-difference reinforcement learning (RL) remains difficult. Effective policy…
Update-Free On-Policy Steering via Verifiers
Maria Attarian, Ian Vyse, Jasper Gerigk +7
In recent years, Behavior Cloning (BC) has become one of the most prevalent methods for learning manipulation from human demonstrations. Despite their successes, BC policies are of…
Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
Xianghao Xu, Yifan Ruan, Srinath Sridhar +1
3D models of manufactured objects are important for populating virtual worlds and for synthetic data generation for vision and robotics. To be most useful, such objects should be a…